PulseAugur
EN
LIVE 12:03:55
Polski(PL) W testach zespołu White Circle metoda RISE doprowadziła do wygenerowania niedozwolonych obrazów w około 13 proc. prób na modelach OpenAI i Google. Skuteczność k

RISE method bypasses OpenAI and Google AI safety filters

By PulseAugur Editorial · [1 sources] ·

A security research team, White Circle Ai, discovered that their RISE method can bypass safety filters in AI models from OpenAI and Google. In approximately 13% of test cases, the method successfully generated prohibited images, with human testers confirming the effectiveness of each attack. AI

IMPACT This research highlights potential vulnerabilities in AI safety mechanisms, suggesting a need for improved filtering and adversarial robustness.

RANK_REASON Research paper detailing a new method that bypasses safety filters in AI models. [lever_c_demoted from research: ic=1 ai=1.0]

Read on Mastodon — mastodon.social →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

RISE method bypasses OpenAI and Google AI safety filters

How we ranked this

Signal score
11 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
Research paper detailing a new method that bypasses safety filters in AI models. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
safety, model release
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. Mastodon — mastodon.social TIER_1 Polski(PL) · aisight ·

    In tests by the White Circle team, the RISE method led to the generation of prohibited images in about 13% of trials on OpenAI and Google models. The effectiveness of k

    W testach zespołu White Circle metoda RISE doprowadziła do wygenerowania niedozwolonych obrazów w około 13 proc. prób na modelach OpenAI i Google. Skuteczność każdego ataku potwierdzili ludzie. # si # ai # sztucznainteligencja # wiadomości # informacje # technologia https:// aisi…

    LINKS aisight.pl/…/metoda-rise-obeszla-filtry-ai aisight.pl/…/Awarie-i-cyberataki-tydzien-…

RELATED ENTITIES

RELATED TOPICS